Related papers: Assessing the Reliability of Deep Learning Classif…
Building reliable classifiers is a fundamental challenge for deploying machine learning in real-world applications. A reliable system should not only detect out-of-distribution (OOD) inputs but also anticipate in-distribution (ID) errors by…
Understanding the spatial arrangement and nature of real-world objects is of paramount importance to many complex engineering tasks, including autonomous navigation. Deep learning has revolutionized state-of-the-art performance for tasks in…
The reliability of deep learning accelerators (DLAs) used in autonomous driving systems has significant impact on the system safety. However, the DLA reliability is usually evaluated with low-level metrics like mean square errors of the…
Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing…
Evaluation of Bayesian deep learning (BDL) methods is challenging. We often seek to evaluate the methods' robustness and scalability, assessing whether new tools give `better' uncertainty estimates than old ones. These evaluations are…
Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but…
Despite many proposed algorithms to provide robustness to deep learning (DL) models, DL models remain susceptible to adversarial attacks. We hypothesize that the adversarial vulnerability of DL models stems from two factors. The first…
Deep learning (DL) has been applied extensively in a wide range of fields. However, it has been shown that DL models are susceptible to a certain kinds of perturbations called \emph{adversarial attacks}. To fully unlock the power of DL in…
Deep Neural Networks (DNN) are core components for classification and regression tasks of many software systems. Companies incur in high costs for testing DNN with datasets representative of the inputs expected in operation, as these need…
Deep Learning (DL) models are widely used in machine learning due to their performance and ability to deal with large datasets while producing high accuracy and performance metrics. The size of such datasets and the complexity of DL models…
The recent advances in machine learning in various fields of applications can be largely attributed to the rise of deep learning (DL) methods and architectures. Despite being a key technology behind autonomous cars, image processing, speech…
Deep learning (DL) models have achieved paradigm-changing performance in many fields with high dimensional data, such as images, audio, and text. However, the black-box nature of deep neural networks is a barrier not just to adoption in…
Deep Neural Networks (DNN) are typically tested for accuracy relying on a set of unlabelled real world data (operational dataset), from which a subset is selected, manually labelled and used as test suite. This subset is required to be…
Deep learning (DL) has become a driving force and has been widely adopted in many domains and applications with competitive performance. In practice, to solve the nontrivial and complicated tasks in real-world applications, DL is often not…
A crucial requirement for reliable deployment of deep learning models for safety-critical applications is the ability to identify out-of-distribution (OOD) data points, samples which differ from the training data and on which a model might…
Deep Reinforcement Learning (DRL) is considered a potential framework to improve many real-world autonomous systems; it has attracted the attention of multiple and diverse fields. Nevertheless, the successful deployment in the real world is…
A growing demand is witnessed in both industry and academia for employing Deep Learning (DL) in various domains to solve real-world problems. Deep Reinforcement Learning (DRL) is the application of DL in the domain of Reinforcement Learning…
Training a deep neural network (DNN) often involves stochastic optimization, which means each run will produce a different model. Several works suggest this variability is negligible when models have the same performance, which in the case…
While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…
Off-policy evaluation and learning (OPE/L) use offline observational data to make better decisions, which is crucial in applications where online experimentation is limited. However, depending entirely on logged data, OPE/L is sensitive to…